from collections import Counter
input_file = r'input_file.txt'
# Main logic
# If hash is different then the contents are different
# If hash is same then the contents may be different
def count_with_index(values):
'''
Returns dict like key: (count, [indexes])
'''
result = {}
for i, v in enumerate(values):
count, indexes = result.get(v, (0, []))
result[v] = (count + 1, indexes + [i])
return result
def get_lines(fp, line_numbers):
return (v for i, v in enumerate(fp) if i in line_numbers)
# Gets hashes of all lines
counter = count_with_index(map(hash, open(input_file)))
# Sums only the unique hashes
sum_of_unique_hash = sum((c for _, (c, _) in counter.items() if c == 1))
# Filters all non unique hashes
non_unique_hash = ((h, v) for h, (c, v) in counter.items() if c != 1)
total_sum = sum_of_unique_hash
# For all non unique hashes get the actual line and count
# One hash is picked per time. So memory is not consumed much.
for h, v in non_unique_hash:
counter = Counter(get_lines(open(input_file), v))
total_sum += sum(1 for k, v in counter.items())
print('Total number of unique lines is : ', total_sum)
下面的逻辑是基于哈希的。它读取每一行的哈希值,而不是整行的哈希值,这使大小最小化。然后比较散列。对于相等的字符串,散列通常是相同的,很少有字符串会发生变化,所以读取实际行并比较实际字符串以确定。下面的内容也适用于大文件。你知道吗
相关问题 更多 >
编程相关推荐